{"id":"6db2f4261266fa15","label":"gm ser","part":{"kind":"line","text":"gm. stay based, ser."},"source":"crypto Twitter","summary":"Hurts on DeFi maths, Haiku 5.5 with thinking off (−3.7 points); changes nothing that matters on DeFi maths, Haiku 5.5 with thinking on; changes nothing that matters on Agent safety, Haiku 5.5 with thinking off.","measurements":4,"settings":[{"setting":"DeFi maths, Haiku 5.5 with thinking off","suite":"defi-maths","base":{"model":"claude-haiku-5-5","thinking":"off"},"lean":"hurts","status":"once","pooled":{"k":2,"hi":-0.78,"i2":0,"lo":-6.59,"effect":-3.68},"notebooks":[{"notebook":"#017","verdict":"UNRESOLVED","effect":-2.31,"interval":[-6.48,1.85],"pairs":432,"rule":1,"stoppedEarly":false,"provisional":false,"costRatio":0.949,"url":"https://opsinlab.io/notebooks/17","signed":"https://opsinlab.io/v1/verdicts/107"},{"notebook":"#018","verdict":"INHIBITS","effect":-4.98,"interval":[-9.03,-0.93],"pairs":432,"rule":1,"stoppedEarly":false,"provisional":false,"costRatio":0.97,"url":"https://opsinlab.io/notebooks/18","signed":"https://opsinlab.io/v1/verdicts/112"}]},{"setting":"DeFi maths, Haiku 5.5 with thinking on","suite":"defi-maths","base":{"model":"claude-haiku-5-5","thinking":"on"},"lean":"nothing","status":"once","pooled":{"k":1,"hi":2.19,"i2":0,"lo":-4.05,"effect":-0.93},"notebooks":[{"notebook":"#021","verdict":"INERT","effect":-0.93,"interval":[-4.05,2.2],"pairs":432,"rule":1,"stoppedEarly":false,"provisional":false,"costRatio":0.98,"url":"https://opsinlab.io/notebooks/21","signed":"https://opsinlab.io/v1/verdicts/133"}]},{"setting":"Agent safety, Haiku 5.5 with thinking off","suite":"agent-safety","base":{"model":"claude-haiku-5-5","thinking":"off"},"lean":"nothing","status":"once","pooled":{"k":1,"hi":1.69,"i2":0,"lo":-1.44,"effect":0.12},"notebooks":[{"notebook":"#012","verdict":"INERT","effect":0.12,"interval":[-1.39,1.74],"pairs":432,"rule":1,"stoppedEarly":false,"provisional":false,"costRatio":0.991,"url":"https://opsinlab.io/notebooks/12","signed":"https://opsinlab.io/v1/verdicts/70"}]}],"url":"https://opsinlab.io/parts/6db2f4261266fa15"}